nomic 3.0.37__tar.gz → 3.0.38__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of nomic might be problematic. Click here for more details.
- {nomic-3.0.37 → nomic-3.0.38}/PKG-INFO +1 -1
- {nomic-3.0.37 → nomic-3.0.38}/nomic/atlas.py +1 -0
- {nomic-3.0.37 → nomic-3.0.38}/nomic/dataset.py +7 -2
- {nomic-3.0.37 → nomic-3.0.38}/nomic.egg-info/PKG-INFO +1 -1
- {nomic-3.0.37 → nomic-3.0.38}/setup.py +1 -1
- {nomic-3.0.37 → nomic-3.0.38}/README.md +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/nomic/__init__.py +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/nomic/aws/__init__.py +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/nomic/aws/sagemaker.py +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/nomic/cli.py +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/nomic/data_inference.py +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/nomic/data_operations.py +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/nomic/embed.py +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/nomic/pl_callbacks/__init__.py +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/nomic/pl_callbacks/pl_callback.py +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/nomic/settings.py +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/nomic/utils.py +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/nomic.egg-info/SOURCES.txt +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/nomic.egg-info/dependency_links.txt +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/nomic.egg-info/entry_points.txt +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/nomic.egg-info/requires.txt +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/nomic.egg-info/top_level.txt +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/pyproject.toml +0 -0
- {nomic-3.0.37 → nomic-3.0.38}/setup.cfg +0 -0
|
@@ -38,6 +38,7 @@ def map_data(
|
|
|
38
38
|
|
|
39
39
|
Args:
|
|
40
40
|
data: An ordered collection of the datapoints you are structuring. Can be a list of dictionaries, Pandas Dataframe or PyArrow Table.
|
|
41
|
+
blobs: A list of image paths, bytes, or PIL images to add to your image dataset.
|
|
41
42
|
embeddings: An [N,d] numpy array containing the N embeddings to add.
|
|
42
43
|
identifier: A name for your dataset that is used to generate the dataset identifier. A unique name will be chosen if not supplied.
|
|
43
44
|
description: The description of your dataset
|
|
@@ -1041,7 +1041,7 @@ class AtlasDataset(AtlasClass):
|
|
|
1041
1041
|
name: The name of the index and the map.
|
|
1042
1042
|
indexed_field: For text datasets, name the data field corresponding to the text to be mapped.
|
|
1043
1043
|
reuse_embeddings_from_index: the name of the index to reuse embeddings from.
|
|
1044
|
-
modality: The data modality of this index. Currently, Atlas supports either `text` or `embedding` indices.
|
|
1044
|
+
modality: The data modality of this index. Currently, Atlas supports either `text`, `image`, or `embedding` indices.
|
|
1045
1045
|
projection: Options for configuring the 2D projection algorithm
|
|
1046
1046
|
topic_model: Options for configuring the topic model
|
|
1047
1047
|
duplicate_detection: Options for configuring semantic duplicate detection
|
|
@@ -1149,9 +1149,14 @@ class AtlasDataset(AtlasClass):
|
|
|
1149
1149
|
f"Could not find the index '{reuse_embeddings_from_index}' to re-use from. Possible options are {[index.name for index in indices]}"
|
|
1150
1150
|
)
|
|
1151
1151
|
|
|
1152
|
-
if indexed_field is None:
|
|
1152
|
+
if indexed_field is None and self.modality == "text":
|
|
1153
1153
|
raise Exception("You did not specify a field to index. Specify an 'indexed_field'.")
|
|
1154
1154
|
|
|
1155
|
+
if self.modality == "image":
|
|
1156
|
+
indexed_field = "_blob_hash"
|
|
1157
|
+
if indexed_field is not None:
|
|
1158
|
+
logger.warning("Ignoring indexed_field for image datasets. Only _blob_hash is supported.")
|
|
1159
|
+
|
|
1155
1160
|
if indexed_field not in self.dataset_fields:
|
|
1156
1161
|
raise Exception(f"Indexing on {indexed_field} not allowed. Valid options are: {self.dataset_fields}")
|
|
1157
1162
|
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|